CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans

TL;DR

CAHAL is a physics-informed, robust super-resolution framework for low-resolution brain MRI scans that enhances resolution while preserving anatomical accuracy for clinical analysis.

Contribution

It introduces a deterministic Mixture of Experts architecture conditioned on resolution and anisotropy, improving super-resolution accuracy and robustness in clinical MRI.

Findings

CAHAL outperforms existing methods in accuracy and efficiency.

It generalizes well across different MRI sequences and acquisition parameters.

The method reduces anatomical distortions common in generative super-resolution.

Abstract

Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice, anisotropic acquisitions prevalent in routine clinical practice. Existing generative super-resolution (SR) methods produce visually compelling isotropic volumes but often introduce anatomical hallucinations, systematic volumetric overestimation, and structural distortions that compromise downstream quantitative analysis and diagnostic safety. To address this, we propose CAHAL (Clinically Applicable resolution enHAncement for Low-resolution MRI scans), a hallucination-robust, physics-informed resolution enhancement framework that operates directly in the patient's native acquisition space. CAHAL employs a deterministic bivariate Mixture of Experts (MoE) architecture routing each input through specialised residual 3D U-Net experts conditioned on both volumetric resolution and acquisition anisotropy, two independent descriptors of clinical MRI acquisition. Experts are optimised with a composite loss combining edge-penalised spatial reconstruction, Fourier-domain spectral coherence matching, and a segmentation-guided semantic consistency constraint. Training pairs are generated on-the-fly via physics-based degradation sampled from a large-scale real-world database, ensuring robust generalisation. Validated on T1-weighted and FLAIR sequences against generative baselines, CAHAL achieves state-of-the-art results, improving the best related methods in terms of accuracy and efficiency.